© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3807
    Prev
    Next
    INDEX
    Explanations

    text from documents or scientific reports that contain mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    HTML tags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.74
    TagMode
    -0.71
     fi
    -0.70
    WindowConstants
    -0.70
    tonode
    -0.69
    IsContent
    -0.69
    MigrationBuilder
    -0.67
     snippetHide
    -0.67
     first
    -0.66
    DeleteBehavior
    -0.66
    POSITIVE LOGITS
    <strong>
    2.73
    <b>
    2.50
    <em>
    2.50
    <i>
    2.44
    <code>
    1.99
    <u>
    1.97
    <sup>
    1.66
    <sub>
    1.60
     
    1.37
    <s>
    1.26
    Activations Density 4.974%

    No Known Activations